metadata
library_name: transformers
license: cc-by-4.0
base_model: l3cube-pune/indic-sentence-bert-nli
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: indic-sentence-bert-nli-hate-mr
results: []
indic-sentence-bert-nli-hate-mr
This model is a fine-tuned version of l3cube-pune/indic-sentence-bert-nli on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1222
- Accuracy: 0.9732
- Precision: 0.9733
- Recall: 0.9732
- F1: 0.9732
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.6323 | 1.0 | 61 | 0.6216 | 0.6819 | 0.6951 | 0.6816 | 0.6762 |
| 0.6538 | 2.0 | 122 | 0.6064 | 0.6843 | 0.7260 | 0.6849 | 0.6695 |
| 0.478 | 3.0 | 183 | 0.6003 | 0.7060 | 0.7076 | 0.7059 | 0.7054 |
| 0.3915 | 4.0 | 244 | 0.5929 | 0.7373 | 0.748 | 0.7376 | 0.7346 |
| 0.3288 | 5.0 | 305 | 0.6091 | 0.7470 | 0.7560 | 0.7472 | 0.7448 |
| 0.2425 | 6.0 | 366 | 0.6779 | 0.7301 | 0.7344 | 0.7300 | 0.7288 |
| 0.1878 | 7.0 | 427 | 0.6804 | 0.7422 | 0.7423 | 0.7422 | 0.7421 |
| 0.1156 | 8.0 | 488 | 0.7229 | 0.7614 | 0.7616 | 0.7615 | 0.7614 |
| 0.1454 | 9.0 | 549 | 0.8009 | 0.7494 | 0.7528 | 0.7493 | 0.7485 |
| 0.1152 | 10.0 | 610 | 0.8109 | 0.7566 | 0.7571 | 0.7566 | 0.7565 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0